Systems and Soft Computing最新文献_第3页

The application of improved DTW algorithm in sports posture recognition 改进的 DTW 算法在运动姿势识别中的应用

Systems and Soft Computing

Pub Date : 2024-10-16 DOI: 10.1016/j.sasc.2024.200163

Changjiang Niu

Sports posture recognition plays a crucial role in modern sports science and training. Posture recognition and analysis plays a positive role in improving sports quality and ensuring sports safety. However, existing recognition technologies still have poor recognition and accuracy in large amounts of posture data. Therefore, to further improve the performance of the existing posture recognition techniques, this study assumes that postures during movement can be effectively represented through the time series of skeletal key points, and the local similarity of these postures can be captured through the Dynamic Time Warping (DTW) algorithm. Based on this assumption, the existing DTW algorithm is improved by introducing the K-Nearest Neighbor (KNN) algorithm and combining it with Principal Component Analysis (PCA) for feature dimensionality reduction. A novel algorithmic model for postures recognition is proposed. The experimental results showed that the improved algorithm performed well in postures recognition rate and accuracy. Especially, when the k value was 5, the recognition rate reached up to 89%, and the accuracy reached 87%. Compared with the existing algorithm, the improved KNN-DTW algorithm has significant improvement in accuracy and computational efficiency. In summary, the new algorithm shows significant advantages in terms of accuracy and stability, providing a powerful tool for the analysis of athletic postures in the field of sports. Meanwhile, this research result has important application prospects in fields such as sports training, sports medicine, and virtual reality.

运动姿势识别在现代体育科学和训练中起着至关重要的作用。姿势识别和分析在提高运动质量和确保运动安全方面发挥着积极作用。然而，现有的识别技术在大量姿势数据中的识别率和准确率仍然较低。因此，为了进一步提高现有姿态识别技术的性能，本研究假设运动时的姿态可以通过骨骼关键点的时间序列得到有效表达，并通过动态时间扭曲（DTW）算法捕捉这些姿态的局部相似性。基于这一假设，通过引入 K 近邻（KNN）算法并结合主成分分析（PCA）进行特征降维，改进了现有的 DTW 算法。提出了一种新的姿态识别算法模型。实验结果表明，改进后的算法在姿势识别率和准确率方面表现良好。特别是当 k 值为 5 时，识别率高达 89%，准确率达到 87%。与现有算法相比，改进后的 KNN-DTW 算法在准确率和计算效率方面都有显著提高。总之，新算法在准确性和稳定性方面具有显著优势，为体育领域的运动姿势分析提供了有力工具。同时，该研究成果在运动训练、运动医学和虚拟现实等领域具有重要的应用前景。

{"title":"The application of improved DTW algorithm in sports posture recognition","authors":"Changjiang Niu","doi":"10.1016/j.sasc.2024.200163","DOIUrl":"10.1016/j.sasc.2024.200163","url":null,"abstract":"<div><div>Sports posture recognition plays a crucial role in modern sports science and training. Posture recognition and analysis plays a positive role in improving sports quality and ensuring sports safety. However, existing recognition technologies still have poor recognition and accuracy in large amounts of posture data. Therefore, to further improve the performance of the existing posture recognition techniques, this study assumes that postures during movement can be effectively represented through the time series of skeletal key points, and the local similarity of these postures can be captured through the Dynamic Time Warping (DTW) algorithm. Based on this assumption, the existing DTW algorithm is improved by introducing the K-Nearest Neighbor (KNN) algorithm and combining it with Principal Component Analysis (PCA) for feature dimensionality reduction. A novel algorithmic model for postures recognition is proposed. The experimental results showed that the improved algorithm performed well in postures recognition rate and accuracy. Especially, when the k value was 5, the recognition rate reached up to 89%, and the accuracy reached 87%. Compared with the existing algorithm, the improved KNN-DTW algorithm has significant improvement in accuracy and computational efficiency. In summary, the new algorithm shows significant advantages in terms of accuracy and stability, providing a powerful tool for the analysis of athletic postures in the field of sports. Meanwhile, this research result has important application prospects in fields such as sports training, sports medicine, and virtual reality.</div></div>","PeriodicalId":101205,"journal":{"name":"Systems and Soft Computing","volume":"6 ","pages":"Article 200163"},"PeriodicalIF":0.0,"publicationDate":"2024-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142538104","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Design and implementation of J2EE-based statement feature recognition in English teaching system optimization 基于 J2EE 的语句特征识别在英语教学系统优化中的设计与实现

Systems and Soft Computing

Pub Date : 2024-10-16 DOI: 10.1016/j.sasc.2024.200162

Lina Wang

With the development of Internet technology, network English teaching system came into being and developed rapidly. Based on optimized J2EE, this paper presents the implementation of sentence feature recognition in the English teaching system. Optimize the load balancing algorithm on the basis of cloud computing technology, and improve the teaching service providing ability of online teaching system based on J2EE. The technology integration of Sturts2, Spring, and Batis was realized to realize the persistence layer, business layer, and presentation layer respectively through the three frameworks. Then, the technology of Struts2 and Spring, Spring, and Batis software is integrated to analyze and build the current popular SSI lightweight framework, and RBAC is used to provide a security mechanism for the SSI framework. It establishes that the information system should adopt the mixed architecture of B/S architecture and C/S architecture, and then design the overall functional structure of the system with students, teachers, and administrators as the main users from the perspective of users. This paper analyzes and explains the overall structure of the J2Ee-based English teaching system, briefly introduces the overall framework of the whole website, and introduces the main functions of each functional module of the website. Finally, the English teaching system based on optimized J2EE statement feature recognition is implemented and tested. In the performance test of file resource query service with virtual 10–100 users and 20 times submitted by each user, the response time of the system is <1.5 s, the success rate reaches 100 %, and the CPU utilization is also <5 %. The memory usage is relatively high. When 2000 queries are concurrent, the memory usage reaches >160 M.

随着互联网技术的发展，网络英语教学系统应运而生并迅速发展。本文基于优化后的J2EE，介绍了句子特征识别在英语教学系统中的实现。在云计算技术的基础上优化负载均衡算法，提高基于J2EE的网络教学系统的教学服务提供能力。实现了 Sturts2、Spring 和 Batis 的技术集成，通过三个框架分别实现了持久层、业务层和表现层。然后，将 Struts2 与 Spring、Spring 和 Batis 软件的技术进行整合，分析并构建了当前流行的 SSI 轻量级框架，并利用 RBAC 为 SSI 框架提供了安全机制。确定信息系统应采用 B/S 架构和 C/S 架构的混合架构，然后从用户的角度出发，以学生、教师和管理员为主要用户设计系统的整体功能结构。本文对基于 J2Ee 的英语教学系统的整体结构进行了分析和阐述，简要介绍了整个网站的整体框架，并介绍了网站各功能模块的主要功能。最后，实现并测试了基于优化的 J2EE 语句特征识别的英语教学系统。在虚拟10-100个用户、每个用户提交20次文件资源查询服务的性能测试中，系统的响应时间为1.5 s，成功率达到100%，CPU利用率也为5%。内存使用率相对较高。当同时进行 2000 次查询时，内存使用量达到 160 M。

{"title":"Design and implementation of J2EE-based statement feature recognition in English teaching system optimization","authors":"Lina Wang","doi":"10.1016/j.sasc.2024.200162","DOIUrl":"10.1016/j.sasc.2024.200162","url":null,"abstract":"<div><div>With the development of Internet technology, network English teaching system came into being and developed rapidly. Based on optimized J2EE, this paper presents the implementation of sentence feature recognition in the English teaching system. Optimize the load balancing algorithm on the basis of cloud computing technology, and improve the teaching service providing ability of online teaching system based on J2EE. The technology integration of Sturts2, Spring, and Batis was realized to realize the persistence layer, business layer, and presentation layer respectively through the three frameworks. Then, the technology of Struts2 and Spring, Spring, and Batis software is integrated to analyze and build the current popular SSI lightweight framework, and RBAC is used to provide a security mechanism for the SSI framework. It establishes that the information system should adopt the mixed architecture of B/S architecture and C/S architecture, and then design the overall functional structure of the system with students, teachers, and administrators as the main users from the perspective of users. This paper analyzes and explains the overall structure of the J2Ee-based English teaching system, briefly introduces the overall framework of the whole website, and introduces the main functions of each functional module of the website. Finally, the English teaching system based on optimized J2EE statement feature recognition is implemented and tested. In the performance test of file resource query service with virtual 10–100 users and 20 times submitted by each user, the response time of the system is <1.5 s, the success rate reaches 100 %, and the CPU utilization is also <5 %. The memory usage is relatively high. When 2000 queries are concurrent, the memory usage reaches >160 M.</div></div>","PeriodicalId":101205,"journal":{"name":"Systems and Soft Computing","volume":"6 ","pages":"Article 200162"},"PeriodicalIF":0.0,"publicationDate":"2024-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142538105","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Advancing sustainable mobility: Dynamic predictive modeling of charging cycles in electric vehicles using machine learning techniques and predictive application development 推进可持续交通：利用机器学习技术和预测性应用开发对电动汽车充电周期进行动态预测建模

Systems and Soft Computing

Pub Date : 2024-10-13 DOI: 10.1016/j.sasc.2024.200157

Biplov Paneru , Durga Prasad Mainali , Bishwash Paneru , Sanjog Chhetri Sapkota

The main goal in this research is to train various machine learning models to predict charging cycles in EV Electric Vehicles) battery systems. The considered models are gradient boosting, random forests, decision trees, and linear regression. Each of these was assessed based on its R-squared score, which is an important statistical measure in indicating the variance proportion yielded by the model. In contrast, the Random Forest model significantly improved, with an R-squared value of 0.83, thereby doing an excellent job in capturing nuances of the data. Only surpassed by the Gradient Boosting model at an astonishing R-squared score of 0.87, it is this excellent score that underlines its capability to predict the outcome quite accurately by modeling complex interrelations. In other words, gradient boosting outran the rest and provided the most robust results concerning drivers of students' performance. It also underlines how important choosing a good model is in educational analytics in order to increase the accuracy of the predictions. The use of these models in the proposed EV Battery Charging Cycle Predictor App results in accurate predictions to aid schedule maintenance and energy-related decisions. This research brings light to the future of advanced machine learning methods in enhancing the battery efficiencies of EVs and the development of electric mobility technologies. It is possible that the future work will imply the additional inclusion of real data and the integration of the application to general energy systems.

本研究的主要目标是训练各种机器学习模型，以预测电动汽车（EV Electric Vehicles）电池系统的充电周期。所考虑的模型包括梯度提升、随机森林、决策树和线性回归。每种模型都根据其 R 平方得分进行评估，R 平方得分是显示模型产生的方差比例的重要统计指标。相比之下，随机森林模型的 R 平方值达到了 0.83，在捕捉数据的细微差别方面表现出色。梯度提升模型的 R 方值达到了惊人的 0.87，仅次于随机森林模型，而这一优异成绩正是其通过模拟复杂的相互关系来准确预测结果的能力的体现。换句话说，梯度提升法超越了其他方法，在学生成绩的驱动因素方面提供了最可靠的结果。这也凸显了在教育分析中选择一个好的模型对提高预测准确性的重要性。在拟议的电动汽车电池充电周期预测器应用程序中使用这些模型，可以获得准确的预测结果，从而帮助制定维护计划和做出与能源相关的决策。这项研究为未来先进的机器学习方法在提高电动汽车电池效率和电动交通技术发展方面带来了曙光。未来的工作有可能意味着将更多的真实数据纳入其中，并将应用集成到通用能源系统中。

{"title":"Advancing sustainable mobility: Dynamic predictive modeling of charging cycles in electric vehicles using machine learning techniques and predictive application development","authors":"Biplov Paneru , Durga Prasad Mainali , Bishwash Paneru , Sanjog Chhetri Sapkota","doi":"10.1016/j.sasc.2024.200157","DOIUrl":"10.1016/j.sasc.2024.200157","url":null,"abstract":"<div><div>The main goal in this research is to train various machine learning models to predict charging cycles in EV Electric Vehicles) battery systems. The considered models are gradient boosting, random forests, decision trees, and linear regression. Each of these was assessed based on its R-squared score, which is an important statistical measure in indicating the variance proportion yielded by the model. In contrast, the Random Forest model significantly improved, with an R-squared value of 0.83, thereby doing an excellent job in capturing nuances of the data. Only surpassed by the Gradient Boosting model at an astonishing R-squared score of 0.87, it is this excellent score that underlines its capability to predict the outcome quite accurately by modeling complex interrelations. In other words, gradient boosting outran the rest and provided the most robust results concerning drivers of students' performance. It also underlines how important choosing a good model is in educational analytics in order to increase the accuracy of the predictions. The use of these models in the proposed EV Battery Charging Cycle Predictor App results in accurate predictions to aid schedule maintenance and energy-related decisions. This research brings light to the future of advanced machine learning methods in enhancing the battery efficiencies of EVs and the development of electric mobility technologies. It is possible that the future work will imply the additional inclusion of real data and the integration of the application to general energy systems.</div></div>","PeriodicalId":101205,"journal":{"name":"Systems and Soft Computing","volume":"6 ","pages":"Article 200157"},"PeriodicalIF":0.0,"publicationDate":"2024-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142538106","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Innovative application of particle swarm algorithm in the improvement of digital enterprise management efficiency 粒子群算法在提高数字化企业管理效率中的创新应用

Systems and Soft Computing

Pub Date : 2024-10-12 DOI: 10.1016/j.sasc.2024.200151

Shengnan Zhang

At present, the management of most enterprises still adopts the traditional business model, which is difficult to meet the requirements of modern informatization. To effectively improve the efficiency of digital enterprise management and solve the limitations of traditional management methods in resource allocation, decision-making, and process optimization, an experiment is proposed for a digital enterprise innovation management method based on Particle Swarm Optimization. The research results show that the method is applied to the enterprise for simulation experiments, and the efficiency obtained after using the method is as high as 99.5 %, which is nearly 2 % higher than the enterprise management efficiency obtained before the method is not used. The results show that the proposed Particle Swarm Optimization has high reliability and accuracy for improving the management efficiency of digital enterprises, and can provide new research directions and ideas for the development and progress of enterprises in the Internet era.

目前，大多数企业的管理仍采用传统的经营模式，难以满足现代信息化的要求。为有效提高数字化企业管理效率，解决传统管理方法在资源配置、决策、流程优化等方面的局限性，提出了基于粒子群优化的数字化企业创新管理方法实验。研究结果表明，将该方法应用于企业进行仿真实验，使用该方法后获得的效率高达 99.5%，比未使用该方法前获得的企业管理效率高出近 2%。结果表明，所提出的粒子群优化法对于提高数字化企业的管理效率具有较高的可靠性和准确性，可以为互联网时代企业的发展和进步提供新的研究方向和思路。

引用次数: 0

Wavelet neural network algorithm for hybrid GA in infrared CO2 gas sensor 用于红外二氧化碳气体传感器混合 GA 的小波神经网络算法

Systems and Soft Computing

Pub Date : 2024-10-12 DOI: 10.1016/j.sasc.2024.200145

Jun Wang, Yuanxi Wang

As the economy develops and the environmental impact of the greenhouse effect becomes more apparent, the need for precise measurement of specific gas concentrations in the air has become increasingly pressing. Nevertheless, as a representative of greenhouse gases, CO₂ gas detectors are susceptible to environmental temperature fluctuations, which impairs the accuracy of detection. To address this issue, the research team innovatively combined the genetic algorithm (GA) and the wavelet neural network (WNN) to develop a solution for the temperature compensation problem of the infrared CO₂ gas sensor. The non-dominant sorted genetic algorithm II (NSGA-II) was integrated into the GA to achieve a balance between the accuracy, complexity, and temperature performance of the model through multi-objective optimization. The results showed that compared with other existing models, the GA-WNN model proposed in this study can significantly reduce the difference between the detected values and the actual environmental values under various temperature conditions when processing data. Especially at an ambient temperature of 49 °C, for a true CO₂ concentration of 2000 ppm, the detection value processed by the GA-WNN algorithm was 2046 ppm, with a relative error of only 2.3 %, far lower than the 9.8 % of Faster RCNN algorithm and 11.5 % of WNN algorithm. The contribution of the research is the proposal of a novel temperature compensation method that significantly enhances the precision of infrared CO₂ gas sensors. This is of paramount importance for enhancing the accuracy of gas detection in environmental monitoring and industrial control.

随着经济的发展和温室效应对环境影响的日益明显，精确测量空气中特定气体浓度的需求日益迫切。然而，作为温室气体的代表，二氧化碳气体检测仪容易受到环境温度波动的影响，从而影响检测的准确性。针对这一问题，研究团队创新性地将遗传算法（GA）和小波神经网络（WNN）相结合，开发出了红外二氧化碳气体传感器温度补偿问题的解决方案。在遗传算法中融入了非优势排序遗传算法 II（NSGA-II），通过多目标优化实现了模型精度、复杂度和温度性能之间的平衡。结果表明，与其他现有模型相比，本研究提出的 GA-WNN 模型在处理数据时能显著减少各种温度条件下检测值与实际环境值之间的差异。特别是在环境温度为 49 °C，真实二氧化碳浓度为 2000 ppm 时，GA-WNN 算法处理的检测值为 2046 ppm，相对误差仅为 2.3%，远低于 Faster RCNN 算法的 9.8%和 WNN 算法的 11.5%。这项研究的贡献在于提出了一种新型温度补偿方法，可显著提高红外二氧化碳气体传感器的精度。这对于提高环境监测和工业控制中的气体检测精度至关重要。

{"title":"Wavelet neural network algorithm for hybrid GA in infrared CO2 gas sensor","authors":"Jun Wang, Yuanxi Wang","doi":"10.1016/j.sasc.2024.200145","DOIUrl":"10.1016/j.sasc.2024.200145","url":null,"abstract":"<div><div>As the economy develops and the environmental impact of the greenhouse effect becomes more apparent, the need for precise measurement of specific gas concentrations in the air has become increasingly pressing. Nevertheless, as a representative of greenhouse gases, CO<sub>2</sub> gas detectors are susceptible to environmental temperature fluctuations, which impairs the accuracy of detection. To address this issue, the research team innovatively combined the genetic algorithm (GA) and the wavelet neural network (WNN) to develop a solution for the temperature compensation problem of the infrared CO<sub>2</sub> gas sensor. The non-dominant sorted genetic algorithm II (NSGA-II) was integrated into the GA to achieve a balance between the accuracy, complexity, and temperature performance of the model through multi-objective optimization. The results showed that compared with other existing models, the GA-WNN model proposed in this study can significantly reduce the difference between the detected values and the actual environmental values under various temperature conditions when processing data. Especially at an ambient temperature of 49 °C, for a true CO<sub>2</sub> concentration of 2000 ppm, the detection value processed by the GA-WNN algorithm was 2046 ppm, with a relative error of only 2.3 %, far lower than the 9.8 % of Faster RCNN algorithm and 11.5 % of WNN algorithm. The contribution of the research is the proposal of a novel temperature compensation method that significantly enhances the precision of infrared CO<sub>2</sub> gas sensors. This is of paramount importance for enhancing the accuracy of gas detection in environmental monitoring and industrial control.</div></div>","PeriodicalId":101205,"journal":{"name":"Systems and Soft Computing","volume":"6 ","pages":"Article 200145"},"PeriodicalIF":0.0,"publicationDate":"2024-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142538103","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Automated painting color matching technology based on semantic intelligence understanding 基于语义智能理解的自动绘画色彩匹配技术

Systems and Soft Computing

Pub Date : 2024-10-10 DOI: 10.1016/j.sasc.2024.200158

Jiayin Zhang

Painting color matching technology is widely used in the production and printing process of products. Traditional painting and color matching have been unable to meet market demands. Based on this, a large-scale corpus under the existing semantic intelligent understanding system is used as the knowledge source. The computer automated painting color matching model is constructed. It is applied in case studies to address issues such as unclear query intentions, mismatched system retrieval terms, and return errors caused by uncertain factors such as synonyms and polysemy. This provides new ideas for the application of semantic intelligence understanding and automated painting color matching technology. The experimental results showed that the precision, recall, and F1 of the method used in the research were 0.8639, 0.8026, and 0.8309, respectively, significantly superior to commonly used methods. This indicates that the proposed automated painting color matching technology based on semantic intelligent understanding has high performance, which can effectively meet the painting color matching requirements.

喷漆配色技术被广泛应用于产品的生产和印刷过程中。传统的涂装配色已无法满足市场需求。基于此，以现有语义智能理解系统下的大规模语料库为知识源，构建了计算机自动绘画配色模型。构建了计算机自动绘画配色模型。通过案例研究，解决了查询意图不明确、系统检索词不匹配、同义词和多义词等不确定因素导致的返回错误等问题。这为语义智能理解和自动绘画配色技术的应用提供了新思路。实验结果表明，研究采用的方法的精确度、召回率和 F1 分别为 0.8639、0.8026 和 0.8309，明显优于常用方法。这表明所提出的基于语义智能理解的自动绘画色彩匹配技术具有较高的性能，能有效满足绘画色彩匹配的要求。

引用次数: 0

Innovative strategies for intelligent services in smart libraries in the information age based on linear discriminant analysis 基于线性判别分析的信息时代智慧图书馆智能服务创新策略

Systems and Soft Computing

Pub Date : 2024-10-09 DOI: 10.1016/j.sasc.2024.200159

Jinying Wang, Yuhua Liang, Jingjing Ma

With the advent of the information age, to provide better services and ensure the security management of libraries, intelligent facial recognition technology has gradually become a hot research direction in library management. Meanwhile, to further improve the comprehensive performance of facial recognition, this study attempts to integrate principal component analysis and linear discriminant analysis on the basis of analyzing the framework of recognition technology. Afterwards, it introduced support vector machines for recognition and classification, and proposed a new recognition model. The experimental results show that the recognition accuracy of the proposed model is up to 97 % in the ORL dataset and 94 % in the Yale dataset. The recognition error rate is as low as 0.1 % when the number of training samples is 215 and the number of iterations is 200. The model has the best recognition performance when the image size is 25 × 25 mm and the number of noises is 10. In addition, the model is particularly effective in recognition on single person color or gray images, with the highest P-value of 98.7 %, the highest R-value of 98.8 %, and the highest F1-value of 97.5 %. These results show that the proposed model significantly improves the accuracy and robustness of face recognition, and provides strong technical support for intelligent service innovation in smart libraries.

随着信息时代的到来，为了给图书馆提供更好的服务，确保图书馆的安全管理，智能人脸识别技术逐渐成为图书馆管理的热点研究方向。同时，为了进一步提高人脸识别的综合性能，本研究在分析识别技术框架的基础上，尝试将主成分分析和线性判别分析相结合。随后，引入支持向量机进行识别和分类，提出了一种新的识别模型。实验结果表明，所提模型在 ORL 数据集中的识别准确率高达 97%，在 Yale 数据集中的识别准确率高达 94%。当训练样本数为 215 个、迭代次数为 200 次时，识别错误率低至 0.1%。当图像大小为 25 × 25 毫米、噪声数量为 10 时，该模型的识别性能最佳。此外，该模型对单人彩色或灰色图像的识别效果尤为显著，最高 P 值为 98.7%，最高 R 值为 98.8%，最高 F1 值为 97.5%。这些结果表明，所提出的模型显著提高了人脸识别的准确性和鲁棒性，为智慧图书馆的智能服务创新提供了有力的技术支持。

{"title":"Innovative strategies for intelligent services in smart libraries in the information age based on linear discriminant analysis","authors":"Jinying Wang, Yuhua Liang, Jingjing Ma","doi":"10.1016/j.sasc.2024.200159","DOIUrl":"10.1016/j.sasc.2024.200159","url":null,"abstract":"<div><div>With the advent of the information age, to provide better services and ensure the security management of libraries, intelligent facial recognition technology has gradually become a hot research direction in library management. Meanwhile, to further improve the comprehensive performance of facial recognition, this study attempts to integrate principal component analysis and linear discriminant analysis on the basis of analyzing the framework of recognition technology. Afterwards, it introduced support vector machines for recognition and classification, and proposed a new recognition model. The experimental results show that the recognition accuracy of the proposed model is up to 97 % in the ORL dataset and 94 % in the Yale dataset. The recognition error rate is as low as 0.1 % when the number of training samples is 215 and the number of iterations is 200. The model has the best recognition performance when the image size is 25 × 25 mm and the number of noises is 10. In addition, the model is particularly effective in recognition on single person color or gray images, with the highest P-value of 98.7 %, the highest R-value of 98.8 %, and the highest F1-value of 97.5 %. These results show that the proposed model significantly improves the accuracy and robustness of face recognition, and provides strong technical support for intelligent service innovation in smart libraries.</div></div>","PeriodicalId":101205,"journal":{"name":"Systems and Soft Computing","volume":"6 ","pages":"Article 200159"},"PeriodicalIF":0.0,"publicationDate":"2024-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142445363","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Takagi-Sugeno fuzzy gain controller for Vehicle-to-Grid (V2G) load frequency control 用于车联网 (V2G) 负载频率控制的高木-菅野模糊增益控制器

Systems and Soft Computing

Pub Date : 2024-10-08 DOI: 10.1016/j.sasc.2024.200150

Marayati Marsadek , Farrukh Nagi , Navinesshani Permal , Agileswari AP Ramasamy , Aidil Azwin

Load Frequency Control (LFC) has gained more importance with the introduction of deregulated Renewable Energy Sources (RES) connectivity with the grid. Electrical Vehicles (EVs) can feed electricity back into the grid in Vehicle-to-Grid (V2G) mode to maintain stability. However, the increasing number of EVs penetrating the grid causes frequency instability in the power system. If required, EVs may utilize bi-directional chargers to transfer power back to the grid in the V2G mode while they are charging or in a grid-connected state, restoring the frequency instability of the grid. The frequency restoration response time is important to reset the grid frequency fluctuations in the shortest time possible to avoid shutting down the power system. This paper presents a Takagi-Sugeno (T-S) fuzzy linear output controller for LFC in two-area systems with tie-line control. This work models EV batteries as a single lump of large-capacity battery energy storage systems. The EV's battery system provides ancillary power to the two-area power system to reset it to a steady state after a load disturbance. The T-S fuzzy controller's linear output dependency on its inputs enables it to respond efficiently to load variations in the nonlinear two-area power systems. The proposed controller parameters are evaluated from stability analyses and its robustness is tested with sensitivity analysis. It is compared with other fuzzy controllers, and it demonstrates a fast-settling time and reduced frequency deviation response.

随着可再生能源（RES）与电网连接管制的放松，负载频率控制（LFC）变得更加重要。电动汽车（EV）可以以车对网（V2G）模式向电网回馈电力，以保持电网稳定。然而，越来越多的电动汽车进入电网会导致电力系统频率不稳定。如果需要，电动汽车可以利用双向充电器，在充电或并网状态下以 V2G 模式将电力输送回电网，从而恢复电网的频率不稳定性。频率恢复响应时间对于在最短时间内重置电网频率波动以避免关闭电力系统非常重要。本文提出了一种高木-菅野（Takagi-Sugeno，T-S）模糊线性输出控制器，用于双区系统中的 LFC，并采用连接线控制。这项工作将电动汽车电池作为大容量电池储能系统的单体进行建模。电动汽车电池系统为两区电力系统提供辅助电源，使其在负载扰动后重置为稳定状态。T-S 模糊控制器的线性输出依赖于其输入，使其能够对非线性双区电力系统中的负载变化做出有效响应。通过稳定性分析对所提出的控制器参数进行了评估，并通过灵敏度分析对其鲁棒性进行了测试。该控制器与其他模糊控制器进行了比较，结果表明，该控制器具有较快的平稳时间和较低的频率偏差响应。

{"title":"Takagi-Sugeno fuzzy gain controller for Vehicle-to-Grid (V2G) load frequency control","authors":"Marayati Marsadek , Farrukh Nagi , Navinesshani Permal , Agileswari AP Ramasamy , Aidil Azwin","doi":"10.1016/j.sasc.2024.200150","DOIUrl":"10.1016/j.sasc.2024.200150","url":null,"abstract":"<div><div>Load Frequency Control (LFC) has gained more importance with the introduction of deregulated Renewable Energy Sources (RES) connectivity with the grid. Electrical Vehicles (EVs) can feed electricity back into the grid in Vehicle-to-Grid (V2G) mode to maintain stability. However, the increasing number of EVs penetrating the grid causes frequency instability in the power system. If required, EVs may utilize bi-directional chargers to transfer power back to the grid in the V2G mode while they are charging or in a grid-connected state, restoring the frequency instability of the grid. The frequency restoration response time is important to reset the grid frequency fluctuations in the shortest time possible to avoid shutting down the power system. This paper presents a Takagi-Sugeno (T-S) fuzzy linear output controller for LFC in two-area systems with tie-line control. This work models EV batteries as a single lump of large-capacity battery energy storage systems. The EV's battery system provides ancillary power to the two-area power system to reset it to a steady state after a load disturbance. The T-S fuzzy controller's linear output dependency on its inputs enables it to respond efficiently to load variations in the nonlinear two-area power systems. The proposed controller parameters are evaluated from stability analyses and its robustness is tested with sensitivity analysis. It is compared with other fuzzy controllers, and it demonstrates a fast-settling time and reduced frequency deviation response.</div></div>","PeriodicalId":101205,"journal":{"name":"Systems and Soft Computing","volume":"6 ","pages":"Article 200150"},"PeriodicalIF":0.0,"publicationDate":"2024-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142433796","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Hybrid data mining and data-driven algorithms for a green logistics transportation network in the post-COVID era: A case study in the USA 后 COVID 时代绿色物流运输网络的混合数据挖掘和数据驱动算法：美国案例研究

Systems and Soft Computing

Pub Date : 2024-10-06 DOI: 10.1016/j.sasc.2024.200156

Sina Abbasi , Seyedeh Saeideh Mousavi , Ebrahim Farbod , Mohammad Yousefi Sorkhi , Mohammad Parvin

This study examines the problem of item allocation in a post-COVID environment with various products and a large customer base. The number of customers has increased due to the rise of internet access and the growing willingness to shop online. Problems such as the timely delivery of goods or services, the selection and destination of orders in decentralized warehouses, and the allocation of warehouses to customers are difficult to overcome with a large variety of items and many customers. It has been proposed that mathematical modeling in combination with meta-heuristic solution techniques solve these problems. However, solving mathematical models is very time-consuming and labor-intensive because there are many different location situations. Due to computing power and memory capacity advances, researchers have been looking at data-driven solutions to these problems. This study aims to tackle the diversity of commodities and the number of consumers in the post-COVID era by proposing a hybrid data-driven approach that combines data mining and mathematical modeling to solve mathematical location models with high accuracy in less time. This paper was implemented based on data from real cases in the USA.

本研究探讨了在后 COVID 环境下的商品分配问题，该环境中存在各种产品和庞大的客户群。由于互联网的普及和网上购物意愿的增强，客户数量有所增加。在商品种类繁多、客户数量众多的情况下，商品或服务的及时交付、分散仓库中订单的选择和去向、客户的仓库分配等问题难以解决。有人建议将数学模型与元启发式求解技术相结合来解决这些问题。然而，由于存在许多不同的位置情况，求解数学模型非常耗时耗力。由于计算能力和内存容量的进步，研究人员一直在寻找数据驱动的解决方案来解决这些问题。本研究旨在通过提出一种数据挖掘与数学建模相结合的混合数据驱动方法，以更短的时间高精度地求解数学定位模型，从而解决后 COVID 时代的商品多样性和消费者数量问题。本文基于美国真实案例的数据实施。

{"title":"Hybrid data mining and data-driven algorithms for a green logistics transportation network in the post-COVID era: A case study in the USA","authors":"Sina Abbasi , Seyedeh Saeideh Mousavi , Ebrahim Farbod , Mohammad Yousefi Sorkhi , Mohammad Parvin","doi":"10.1016/j.sasc.2024.200156","DOIUrl":"10.1016/j.sasc.2024.200156","url":null,"abstract":"<div><div>This study examines the problem of item allocation in a post-COVID environment with various products and a large customer base. The number of customers has increased due to the rise of internet access and the growing willingness to shop online. Problems such as the timely delivery of goods or services, the selection and destination of orders in decentralized warehouses, and the allocation of warehouses to customers are difficult to overcome with a large variety of items and many customers. It has been proposed that mathematical modeling in combination with meta-heuristic solution techniques solve these problems. However, solving mathematical models is very time-consuming and labor-intensive because there are many different location situations. Due to computing power and memory capacity advances, researchers have been looking at data-driven solutions to these problems. This study aims to tackle the diversity of commodities and the number of consumers in the post-COVID era by proposing a hybrid data-driven approach that combines data mining and mathematical modeling to solve mathematical location models with high accuracy in less time. This paper was implemented based on data from real cases in the USA.</div></div>","PeriodicalId":101205,"journal":{"name":"Systems and Soft Computing","volume":"6 ","pages":"Article 200156"},"PeriodicalIF":0.0,"publicationDate":"2024-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142419778","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Dynamic ranking function to optimize transshipment costs in intuitionistic Type-2 and Type-1 fuzzy environments 在直观 2 类和 1 类模糊环境中优化转运成本的动态排序函数

Systems and Soft Computing

Pub Date : 2024-09-29 DOI: 10.1016/j.sasc.2024.200153

Tarun Kumar , Sadhna Chaudhary , Kapil Kumar , Kailash Dhanuk , M.K. Sharma

In the dynamic realm of organizational logistics, accurately minimizing transportation and transshipment costs is crucial, yet often challenging due to inherent uncertainties. This paper introduces a novel application of fuzzy logic to provide a more precise analysis of these costs. Specifically, it develops an innovative ranking function for trapezoidal fuzzy numbers (TrFNs) for Type-2 and Type-1 fuzzy environments, a tool yet unexplored in existing literature. The main contributions of this paper are the idea that a ranking function for TrFNs can significantly improve decision-maker's freedom in cost analysis due to an adherence on all (a, b, c d) parameters of TrFN. A new decision-oriented ranking method for these fuzzy numbers is developed which consists of an inventive algorithm. The method is also considered for intuitionistic TrFNs and applied to solve transshipment costs in fuzzy area. To verify the proposed methodology's efficiency, effectiveness and accuracy a numerical example in Wolfram Mathematica 9.0 is demonstrated showing superior computational performance over existing methods.

在动态的组织物流领域，准确地将运输和转运成本降至最低至关重要，但由于固有的不确定性，这往往具有挑战性。本文介绍了一种新颖的模糊逻辑应用，可对这些成本进行更精确的分析。具体来说，它为梯形模糊数 (TrFN) 开发了一种创新的排序功能，适用于 2 类和 1 类模糊环境，这是一种在现有文献中尚未开发的工具。本文的主要贡献在于：由于坚持使用梯形模糊数的所有（a, b, c d）参数，梯形模糊数的排序函数可以显著提高决策者在成本分析中的自由度。针对这些模糊数开发了一种新的面向决策的排序方法，其中包括一种创造性的算法。该方法也适用于直观 TrFN，并被应用于解决模糊区域的转运成本问题。为了验证所提方法的效率、有效性和准确性，在 Wolfram Mathematica 9.0 中演示了一个数值示例，显示出优于现有方法的计算性能。

{"title":"Dynamic ranking function to optimize transshipment costs in intuitionistic Type-2 and Type-1 fuzzy environments","authors":"Tarun Kumar , Sadhna Chaudhary , Kapil Kumar , Kailash Dhanuk , M.K. Sharma","doi":"10.1016/j.sasc.2024.200153","DOIUrl":"10.1016/j.sasc.2024.200153","url":null,"abstract":"<div><div>In the dynamic realm of organizational logistics, accurately minimizing transportation and transshipment costs is crucial, yet often challenging due to inherent uncertainties. This paper introduces a novel application of fuzzy logic to provide a more precise analysis of these costs. Specifically, it develops an innovative ranking function for trapezoidal fuzzy numbers (TrFNs) for Type-2 and Type-1 fuzzy environments, a tool yet unexplored in existing literature. The main contributions of this paper are the idea that a ranking function for TrFNs can significantly improve decision-maker's freedom in cost analysis due to an adherence on all (a, b, c d) parameters of TrFN. A new decision-oriented ranking method for these fuzzy numbers is developed which consists of an inventive algorithm. The method is also considered for intuitionistic TrFNs and applied to solve transshipment costs in fuzzy area. To verify the proposed methodology's efficiency, effectiveness and accuracy a numerical example in Wolfram Mathematica 9.0 is demonstrated showing superior computational performance over existing methods.</div></div>","PeriodicalId":101205,"journal":{"name":"Systems and Soft Computing","volume":"6 ","pages":"Article 200153"},"PeriodicalIF":0.0,"publicationDate":"2024-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142419775","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0